Anthropic shipped two new features for Claude over the past couple of days, but as far as I can tell they didn't provide any documentation at all beyond a tweet about each one … so I reverse engineered the system prompt to figure out how they work
CODE
-
AI Model Performance Assessment on Coding Tasks
By
–
This is quite good though But tested on some coding tasks, didn't seem that much better
-
Mixture-of-Recursions: Adaptive Computation for Language Models
By
–
What if language models could learn to "think harder" only when they need to—allocating deep computation to challenging tokens while breezing through simple ones? We're excited to have Reza tomorrow in our AI4Science community giving a talk on Mixture-of-Recursions!
-
LoRA Compatibility and Retraining Strategies for AI Models
By
–
they are compatible with LoRAs. that doesn’t mean that LoRAs are pluggable *as-is*. While we’ve found that LoRAs sometimes work well or even better plugging them as is, we’ve found better results by retraining them for the most part. The important part is the compatibility.
-
Weaver Combines Weak Verifiers to Boost LLM Output Quality
By
–
New from Snorkel AI: Weaver combines weak verifiers to boost LLM output quality: no fine-tuning needed. +14.5% accuracy 98.2% of gains, 99.97% less compute (via distillation) Outperforms naive voting, rivals GPT-4o Read the full paper
-
LLM Safety: Why Current Development Approaches Are Insufficient
By
–
That's the whole problem. We are developing software against LLMs in the same way we use SQL: we write our own instructions as a programmer, then we combine them with input from our users With SQL we can do that safely. With LLMs we can't
-
Demanding Reliable Application Security Solutions
By
–
I disagree: when it comes to application security I think it's acceptable for us to demand solutions that reliably protect us
-
Claude 4 Best Model for Code According to Developer
By
–
Claude 4 is probably the best model for code right now – I suggest trying Gemini 2.5 Pro and OpenAI o3 if Claude 4 isn't working for you, but they are all about the same level as each other
-
19th Cowboys 20th Flyboys 21st Codeboys Evolution
By
–
19th century: Cowboys
20th century: Flyboys
21st century: Codeboys